Once the deal is closed, the CARMERA team will report into the Automated Mapping Platform (“AMP”) organization of Woven Alpha, Inc. (“Woven Alpha”). Woven Alpha focuses on exploring new strategic areas for business expansion and incubates several innovative projects such as Woven City and Arene, which is Woven Planet’s open software platform. AMP is a connected crowdsourced software platform that supports the creation, development and distribution of high definition (“HD”) maps—a key enabler for smart and safe automated mobility.

The Woven Alpha team plans to develop AMP to become the most globally comprehensive road and lane network HD map platform, enabling high-precision localization support to automated vehicles. The acquisition of CARMERA will accelerate AMP’s shift from the R&D stage to the next phase of commercialization by bolstering the platform’s engineering team with top experts in the development of HD maps. In addition, it will provide access to CARMERA’s sophisticated map update, change management and IoT sensing technology.

Together, the teams will tap into CARMERA’s ability to successfully update HD maps from crowdsourced, camera-based inputs—a significantly cheaper and faster approach than traditional methods. This will strengthen AMP’s ability to serve a comprehensive set of road classes and features, reflecting changes in lane markings, traffic signals, signs and more in near real-time, and support its future multi-regional commercial launch.

CARMERA will join Woven Planet Group as a wholly-owned subsidiary, expanding the company’s footprint beyond its Tokyo headquarters by adding New York and Seattle offices to its planned offices in Silicon Valley and London.

The new TomTom Virtual Horizon is designed to democratize ADAS by supporting vehicles without embedded navigation, as well as the most technologically advanced automated vehicles. The software translates highly attributed map data into actionable information for drivers and vehicles alike. For example, if there is a sharp bend in the road or a change in the speed limit ahead, TomTom Virtual Horizon will warn drivers in non-automated vehicles to prepare to take action, while the software in automated vehicles will enable more informed and intelligent decision making without the involvement of the driver.

TomTom Virtual Horizon offers automakers an all-in-one solution that includes precise positioning, intelligent route prediction, and a horizon provider compliant with industry standard protocols. The new software is built on TomTom’s trusted ADAS map that powers millions of automated vehicles around the world. The solution supports all the TomTom ADAS Map’s road attributes including speed limits, traffic signs, gradient, curvature, lane information and traffic lights. TomTom Virtual Horizon and the TomTom ADAS Map combine for the only all-in-one advanced driver assistance systems offering. Use cases for the solution include predictive powertrain control to minimize emissions as well as improved battery management for hybrid and electric vehicles.

TomTom Virtual Horizon is delivered via automakers’ preferred data format for easy implementation, and the software leverages existing connectivity where available or works fully offline, minimizing onboard hardware costs.

The new software will make it easy for automakers to comply with upcoming Intelligent Speed Assistance (ISA) regulations, including the legislation adopted by the European Commission for the EU that comes into effect as of July 2022. TomTom Virtual Horizon is now in production with multiple global brands.

This is the first published industry standard for the Highly Automated Driving Map production industry in China. It provides a unified set of standards for the development of the Highly Automated Driving Map and defines and standardizes Highly Automated Driving Map acquisition elements. It also sets the foundation for future intelligent and connected vehicles Highly Automated Driving Map exchange formats and for mapping- and positioning-related standard systems for a cohesive and intelligent network.

The standard, whose development was led by EMG over the course of 16 months, was jointly completed by more than 20 companies, including map manufacturers, hardware and software manufacturers in the field of autonomous driving, and automobile manufacturers.

It will also explore the technical requirements of using AMP with Mitsubishi Fuso ADAS, and identify the advantages of using its high-definition maps over conventional maps. Between the two companies, more than ten distinct use cases have been identified. The first Proof of Concept (PoC) will focus on the application of AMP to provide an accurate Entering Curve Speed Warning (ECSW) – developed by Mitsubishi Fuso using their heavy-duty Super Great trucks. This feature predicts the safest speed and gives advanced warning on how to approach an upcoming sharp curve, based on the vehicle’s condition. The results of this research will set the baseline for one of the ADAS performance upgrades available for commercial vehicles. Likewise, this technology will introduce more opportunities for collaboration with users and vehicle manufacturers outside the Toyota Group – particularly those interested in taking advantage of enhanced mapping information to realize ADAS and autonomous functionality in their vehicles.

The traditional solution for safety systems that use mapping technology has been to leverage navigation maps (due to their relatively low cost). However, a lack of real-time updates means these maps are often out of date, posing a risk for vehicles with higher levels of autonomy. Furthermore, their low accuracy makes it difficult to develop precise applications that operate safely at the lane level. Navigation maps also do not account for the relationship between road objects, commonly known as semantics. While it is relatively straightforward to deploy survey vehicles to generate the initial mapping data, the instruments are highly specialized and often expensive to operate. This leads to map maintenance being costly and time-consuming, further reducing the updates that can be deployed to end-users.

For ADAS and automated driving functions to operate safely, regular changes to road markings, road geometry, or structural changes need to be reflected quickly into the HD maps. AMP is able to solve these issues by automating the fusion of near real-time data from vehicle fleets as well as wide area coverage satellite and aerial imagery – dramatically improving map update frequency, coverage, and cost.

As part of the first PoC, both companies will test Mitsubishi Fuso’s ESCW feature in conjunction with Woven’s AMP. Woven say that supporting the feature will showcase how AMP can provide immediate safety benefits for the driver and their vehicle. The system’s ability to anticipate road and lane conditions is a particularly important safety feature for commercial vehicle drivers.

Maps that are accurate to within a few meters are good enough when providing turn-by-turn directions for humans. AVs, however, require much greater precision. They must operate with centimeter-level precision for accurate localization, the ability of an AV to locate itself in the world.  

Proper localization also requires constantly updated maps. These maps must also reflect current road conditions, such as a work zone or a lane closure. These maps need to efficiently scale across AV fleets, with fast processing and minimal data storage. Finally, they must be able to function worldwide. 

DeepMap was founded five years ago by Wu and Mark Wheeler, veterans of Google, Apple and Baidu, among other companies. The U.S.-based company has developed a high-definition mapping solution that meets these requirements and has already been validated by the AV industry with a wide array of potential customers around the world.  

The team, primarily located in the San Francisco Bay Area, has many decades of collective experience in mapping technology and developed a solution that considers autonomous vehicles both map creators and map consumers. Using crowdsourced data from vehicle sensors lets DeepMap build a high-definition map that’s continuously updated as the car drives. 

Ongoing Partner Support  

NVIDIA will continue working with DeepMap’s ecosystem to meet their needs, investing in new capabilities and services for new and existing partners. 

NVIDIA DRIVE is a software-defined, end-to-end platform — from deep neural network training and validation in the data center to high-performance compute in the vehicle — that enables continuous improvement and deployment via over-the-air updates.  

DeepMap’s technology will bolster the mapping and localization capabilities available on NVIDIA DRIVE, ensuring autonomous vehicles always know precisely where they are and where they’re going. 

AMP is a connected crowdsourced software platform that supports the creation, development and distribution of high definition (“HD”) maps―a key enabler for smart and safe automated mobility. AMP provides high-precision data driven maps by utilizing vehicle fleet data and advanced satellite imagery technology. AMP HD map includes several layers of data rich information of road objects such as lanes, road signs, traffic lights, and other objects, as well as that of road curves and topography creating an accurate representation of the road while keeping it updated. The Woven Alpha team plans to develop AMP to become the most globally comprehensive road and lane network HD map platform enabling high-precision localization support to automated driving vehicles.

With the aim of realizing smarter and safer logistics through automated driving and Advanced Driver Assistance System (“ADAS”) using HD maps, Isuzu and Hino will examine the potential application of AMP on the domain of small commercial-purpose trucks. The initiative aims to contribute to the dissemination of safer automated driving and ADAS with Commercial Japan Partnership Technologies Corporation that intends to accelerate CASE responses, which Toyota announced with Isuzu and Hino.

First launched in the San Francisco Bay Area with HD map provider Ushr Inc. as an initial pilot partner, CARMERA’s Inventory Map provides change data with greater speed, accuracy and detail than traditional news-aggregation and crowdsourcing services. Using best-in-class traffic-sign recognition, localization and impact analysis, Inventory Map provides specific details and the precise latitude and longitude coordinates for each change, delivering the data via an open, format-agnostic API for easy integration.

Having an accurate, up-to-date picture of essential road signs and markings is critical for autonomous, advanced driver assistance and consumer applications—allowing for more expansive autonomous vehicle operating domains, more efficient commercial routing and more precise directions for consumer navigation. Neither traditional real-time traffic applications, incident-reporting services, nor public records provide the accuracy, detail or comprehensiveness necessary to support the full range of these applications.

For example, in the first four weeks of operation, none of the changes identified by Inventory Map had specific descriptions in public records, even though 49 percent of said changes created alterations to road rules or function.                                                                                                                

Inventory Map joins Events Map, which was launched in 2020 and provides the real-time location of traffic-impacting events like construction at 10x the detail of the next best alternative. They will soon be joined by CARMERA’s Regenerative Map, which provides full camera-based HD map updates.

Convex, Chordant’s mobility data exchange, collaborates with different parts of the mobility eco-system to enable data-driven solutions and services that can help ensure safer, cleaner, and better transportation. Created with direct support from the UK Government Centre for Connected and Autonomous Vehicles (CCAV), Convex sits at the intersection between Connected and Autonomous Vehicles, Intelligent Transport Infrastructure, Digitised Freight and Logistics and Mobility-based Services, supporting the development of end-to-end solutions that depend on the efficient exchange of dynamic mobility data between organisations and technology. Through this partnership, Mobileye will leverage Convex to build mobility solutions that enable a safer, more convenient future of transportation in the West Midlands. 

TfWM, like other strategic transport authorities, have indicated a strong desire to build and maintain a digital record of the regional road network and its ongoing condition to enable new outcomes, both in operating and maintaining the network, and to allow new connected and autonomous services to operate on it efficiently. The key challenge is in providing solutions that can deliver this digital information in a way that integrates with transport authority systems and processes whilst being cost-effective and sustainable.

The partnership between Mobileye and Chordant will see the delivery of a digital record of road assets to allow both TfWM and other local authorities to evaluate how this information can be captured, delivered, used, and maintained.

Automated driving in consumer vehicles requires a 3D roadmap with more detail and accuracy than for navigation or advanced driver assistance systems. Also required is software that “localizes,” or tracks vehicle position, within 10 cm in all drivable conditions and all normally traveled locations. For automated driving to function safely and reliably, the map must receive frequent updates across the entire road network. In addition, the entire solution must be affordable for consumer vehicles.

Founded by Navteq (now HERE) founder and former CEO T. Russell Shields, RoadDB spent six years developing AI software that processes data crowdsourced from cameras and other sensors already available in consumer vehicles to create a precise map that is updated wirelessly with little data usage. RoadDB’s approach generates and updates the map more quickly and affordably than survey vehicles. In addition, RoadDB’s localization software holds up even in rain and snow, on desert roads, and in tunnels and urban canyons.

Shields founded RoadDB in 2014 with proceeds from the 2008 sale of Navteq to Nokia for $8.1 billion. RoadDB received $95 million in private funding through December 2020. Shields says that, based on conservative business models, RoadDB is well positioned to achieve over $100 million in annual revenue by 2025 and a valuation of over $10 billion by 2028.

EMG recently worked with BAIC BJEV to provide HD map services in autonomous valet parking (“AVP”) for BAIC New Energy vehicles. The two parties will cooperate in depth on L3 (conditional driving automation) to L4 (high driving automation) autonomous driving related projects.

Velodyne’s Puck LITE sensors enable GeoSLAM systems to achieve data capture of intricate measurements from up to 100 meters away, delivering rapid results that can save time and money. ZEB-HORIZON addresses a wide variety of solutions, including building information modeling (BIM), construction, real estate, surveying and mining. In an innovative application, Virginia Tech researchers are bringing a World War I battlefield to classrooms and museums with ZEB-HORIZON mapping as part of a virtual reality experience. GeoSLAM scanners are also being deployed by Entropy Group to map K-12 schools in the United States to provide first responders with detailed floor plans in emergency situations.

Velodyne Puck LITE sensors deliver a high-resolution image to measure and analyze indoor, outdoor and underground environments. Designed for applications that require a sensor with a low weight and compact size, the Puck LITE delivers outstanding resolution and performance for UAV/drone, handheld and vehicle applications. It provides a full 360-degree environmental view to deliver real-time 3D data.

This was achieved with TRI-AD test vehicles equipped with DENSO sensors, TRI-AD’s Automated Mapping Platform (AMP), and TomTom’s cloud-based transactional mapping platform. The vehicle sensors are used to collect road observations, which are converted and corrected by TRI-AD’s AMP, for input into TomTom’s cloud-based transactional mapping platform.

These crowdsourced map updates are achieved with TomTom Roadagrams, highly accurate map snippets from car sensors, that TomTom uses to ensure the TomTom HD Map reflects the reality of the road. Combined with sensor data from survey vehicles, this process enables TomTom to maintain the accuracy of its HD map.

Toyota Research Institute-Advanced Development and leading road intelligence company CARMERA announced new results from their ongoing partnership. A follow-up to the companies’successful camera-based mapping work in Tokyo, this latest phase used commercially available dashboard-mounted cameras to detect key road features with the relative accuracy performance necessary for automated driving. Specifically, CARMERA’s machine learning, computer vision and geospatial technologies were used to detect and place key road features—such as lane markings, traffic signals and signs—along Michigan roadways in central Detroit and Ann Arbor.

These results validate TRI-AD and CARMERA’s vision to use street-level cameras from production vehicles, as well as aftermarket telematics systems, to produce comprehensive, accurate mapping data for both horizontal and vertically positioned roadway features. This shared objective stems from both companies’ mission to achieve significant reduction in costs and massive expansion in geographic scope of autonomy, allowing it to scale to more people in more places.

The initiative between the two companies used the same technology that powers CARMERA’s Real-Time Events and Change Management engine, which detects, validates and delivers navigation-critical updates to CARMERA’s regenerative HD mapping system in minutes rather than months. Hardware-agnostic, yet anchored to “ground truth,” the technology unlocks the potential of lower cost sensors and the vast array of existing vehicle probes to help maintain HD maps everywhere.

Tactile Mobility’s newfound commercial relationship with HERE will accelerate the sale of tactile data to companies seeking to develop services and products based on how vehicles “feel” the road. The HERE Marketplace will enable large collections of tactile data to be brought to market for a range of potential customers and support the easy transmission of data for new location-based applications and solutions.

Currently embedded in multiple major car manufacturers’ vehicles, Tactile Mobility’s software utilizes a vehicle’s built-in, non-visual sensor data, including wheel speed, wheel angle, RPM, and more, to calculate valuable information on vehicle-road dynamics and to create two data models that enable safer and more enjoyable driving in diverse environments: VehicleDNA, a representation of each vehicle’s unique characteristics, including engine and braking efficiency, tire health, and fuel consumption; and SurfaceDNA, a mapping layer of road conditions and hazards that offers an in-depth and real-time view of driving environments to support planned maintenance, live hazard detection, post-accident analysis, and more.

Road condition data sourced from Tactile Mobility’s unique tactile sensing technology will be shared on the HERE Marketplace for purchase by a range of data-seeking customers, including automakers and municipalities, to fulfill diverse industry needs. Tactile Mobility will contribute over 10 terabytes of data on road conditions including grip levels and pavement surface conditions, collected across more than 1.5 billion road segments of 30 meters across Europe and North America. The company’s ability to gather and transform previously inaccessible tactile data into actionable insights for entities across the transportation and municipal sectors makes it a major player in the quest to make smart mobility and smart cities a reality.  

Academy of Robotics and Eurovia UK announced plans for a national partnership to trial the use of Kar-go’s autonomous vehicle technology to support urban and rural highway management and to accelerate the “training” of Kar-go to navigate on unmarked roads in the UK.

Academy of Robotics is the startup behind Kar-go, Europe’s first road-based autonomous delivery vehicle. Originally developed to dramatically reduce both the financial and environmental costs of last-mile parcel delivery, Eurovia UK recognised its potential for use in infrastructure and urban development work and is keen to test the Kar-go technology to automate the delivery of small plant equipment, tools, materials and other components to and from a highway work site as well as the potential use of data collected by Kar-go as it travels, to determine the condition of roads.

Eurovia UK, a leading specialist in operating, maintaining and improving road, highway and public realm infrastructure will help Academy of Robotics to scale their training of autonomous vehicles. This will be enabled by accessing digital camera data gathered by Eurovia’s fleet in the UK, which covers over 50,000 kms of UK roads.

The trial will initially focus on the UK, but as a global business operating in 15 countries, the deal offers significant potential for international expansion in Europe and North America.

Understanding hazards – shadows vs. potholes
Through their unique approach to colour perception, Academy of Robotics have been able to address the challenge of environmental variability and ‘noise’ caused by shadows and bright reflections meaning that Kar-go’s operating system is already able to understand the difference between features such as cracks, puddles, potholes and shadows.

As part of the collaboration, HELLA Aglaia will use AutoStream – TomTom’s innovative map delivery system – to access the latest TomTom HD Map on demand and will use the HD Map in the vehicle for accurate localization. In addition, HELLA Aglaia will share processed camera data to TomTom’s cloud-based mapping system for autonomous driving, updating the TomTom HD Map in real time. This will be achieved by generating crowdsourced map updates called Roadagrams which are used to ensure the HD Map reflects the reality of the road. TomTom AutoStream then delivers the updated map data back to the vehicle. The technology will be demonstrated to automakers and Tier 1s by the end of the year.

DMP Group will further expand map coverage from highways to surface roads and from Japan and North America to other regions worldwide.

DMP Group will provide HD Maps across the spectrum of vehicles—personal, fleet, and commercial—as well as provide data for other uses including infrastructure management, maintenance, simulation and analytics, with the vision of becoming the leading provider of digital infrastructure data which serves as a foundation for a safe, smart, and seamless society.

Lear’s EXO high-accuracy vehicle positioning technology is a proprietary Global Navigation Satellite System (GNSS) solution designed to meet the demands of the automotive industry and drive change through increased accuracy, reliability and functional safety in vehicle positioning.

The EXO Technology Partnership Program is a collaborative effort between Lear, automotive OEMs and other ecosystem players that provides a full, automotive-grade solution for V2X and Level 2/3 autonomous driving features.

Lane Hazard Warning enables an event detected by a vehicle’s sensors – such as a disabled or slow car, a slippery road, debris or a pothole – to be precisely localized to a specific lane and this information to be transmitted in real‐time via the cloud to other vehicles approaching the same area.

Lane Hazard Warning utilizes a vehicle’s sensors together with HD Locator, Mitsubishi Electric’s precise centimeter‐level positioning technology, and the HERE Open Location Platform, the collaborative big location data platform.

As part of their broad collaboration, the companies are also evaluating the application of the technology in automated updates of maps for automated vehicles using the cloud as well as in a service that alerts cities and road maintenance authorities to road surface degradation.

Designated as Korea’s first free economic zone, IFEZ consists of Songdo, Yeongjong and Cheongna International Cities with a total size of 132.9 km².

SK Telecom will create an HD map covering the entire IFEZ area starting with Songdo International City. An HD map is a machine-readable map with centimeter-level accuracy, offering essential information for self-driving, including lanes, road conditions, speed limits and road slopes. Thus, it is regarded as a key element for achieving Level 4 of autonomy for autonomous vehicles as defined by the Society of Automotive Engineers.

The HD map will be built with ‘Dynamic Data Platform,’ a 5G-based real-time update solution for HD maps. Dynamic Data Platform automatically updates HD maps upon receiving road observation data from Advanced Driver Assistance Systems (ADAS) over 5G network. SK Telecom plans to install ADAS and 5G communication modules to public transport vehicles and official/government cars in the IFEZ area to detect all changes in the road environment.

Moreover, SK Telecom and the IFEZ Authority will build a data hub to systematically manage and analyze data of the floating population to enhance the convenience and safety of citizens through smarter transportation policies.